growth-strategy

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This skill auto-chains and ingests the output of the competitor-research skill (Step 0.2) by loading data/competitors_.json and pasting the "rivals" markdown back into the conversation, and the LLM is explicitly required to read that competitor evidence (derived from public competitors/rivals data) to generate and pick growth strategies — exposing the agent to untrusted, third-party content that can change behavior.